CtrlK
BlogDocsLog inGet started
Tessl Logo

macios-ci-postmortem

Post-mortem analysis of CI failures across recent PRs in dotnet/macios. Identifies flaky tests, infrastructure issues, and shared regressions by analyzing builds from the last week. Files or updates GitHub issues for failures unrelated to any specific PR. Use when asked to "find flaky tests", "CI post-mortem", "what's been failing in CI", or "file issues for flaky failures".

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, highly actionable workflow with clear sequencing and proper validation/confirmation gates for its destructive issue-filing operations. Strong on every dimension; the main lever is tighter conciseness and possibly splitting more reference material out of the main body.

Suggestions

Trim the verbose issue-body markdown templates (e.g. Step 4.5) into shorter skeletons, leaving prose elaboration to be filled at execution time.

Consider moving the detailed build-failure/binlog handling (Step 2.6a) into a dedicated reference file to reduce body length and improve progressive disclosure.

A few long command blocks could be consolidated with shared variable definitions to cut repeated --org/--project boilerplate.

DimensionReasoningScore

Conciseness

Mostly efficient and dense with actionable detail, avoiding filler explanations of concepts Claude already knows, though some issue-body templates and the build-failure subsection could be trimmed.

4 / 5

Actionability

Provides extensive copy-paste-ready bash, python, and sql commands with real flags and concrete examples covering discovery, extraction, classification, and issue filing.

5 / 5

Workflow Clarity

A clear four-phase sequence with numbered steps and explicit validation/confirmation checkpoints — TestSummary filtering before deep downloads, root-cause identification rules, and mandatory user confirmation before any issue filing.

5 / 5

Progressive Disclosure

Well-organized into phases with a clearly signaled, one-level-deep reference (references/azure-devops-cli.md, a real file); the bulk of workflow detail is inline, which is reasonable but makes the 740-line body somewhat monolithic.

4 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-scoped description that clearly states concrete capabilities and provides explicit trigger guidance tied to natural user phrasing. Minor room to broaden synonym coverage, but it cleanly answers both what and when.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Identifies flaky tests, infrastructure issues, and shared regressions', 'analyzing builds from the last week', 'Files or updates GitHub issues' — with comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both what (post-mortem analysis, classification, issue filing) and when (a 'Use when asked to...' clause with concrete quoted trigger phrases).

5 / 5

Trigger Term Quality

Includes several natural trigger phrases users would say ('find flaky tests', 'CI post-mortem', 'what's been failing in CI', 'file issues for flaky failures'), though a few natural synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Targets a clear, repo-specific niche (dotnet/macios CI post-mortem) with distinct triggers, making conflict with other skills unlikely.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (742 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 2 missing

Warning

Total

14

/

16

Passed

Repository
dotnet/macios
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.